Example methods, apparatus, systems and articles of manufacture are disclosed to determine tags for unknown media using multiple media features. Disclosed examples extract features from portions of the unknown media. Disclosed examples weight the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features. Disclosed examples search a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media, the list of suggested tags including relevancy scores for respective ones of the tags in the list. Disclosed examples assign a tag from the list of suggested tags to the unknown media based on a comparison of the relevancy score for the tag to a threshold.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A system for tagging a media segment, the system comprising: a processor; and a non-transitory computer readable medium having stored therein instructions that, when executed by the processor, cause performance of operations comprising: extracting features from a media segment to generate a plurality of extracted features; determining weights for the plurality of extracted features, wherein each weight for each extracted feature is based on a type of automated features extraction method used to generate the extracted feature; determining weighted features corresponding to the plurality of extracted features by weighing the extracted features using the weights determined based on the different types of automated feature extraction methods; searching a known tag database based on the weighted features, the known tag database including data indicative of extracted media features associated with one or more tags applied to respective ones of pre-tagged media segments; identifying, based on the searching the known tag database, a list of suggested tags corresponding to the media segment, each of the suggested tags in the list of suggested tags including a relevancy score; obtaining an indication of approval to associate at least one of the suggested tags with the media segment; and responsive to the obtaining the indication of approval, tagging the media segment with the at least one of the suggested tags by storing, in the known tag database, data indicative of the weighted features in association with the at least one of the suggested tags associated with the media segment.
2. The system of claim 1, wherein the system further includes a user interface, and wherein obtaining the indication of approval is performed by: presenting, via the user interface, a prompt requesting approval to associate the at least one of the suggested tags with the media segment; and receiving, via the user interface, the indication of approval to associate the at least one of the suggested tags with the media segment.
3. The system of claim 1, wherein the operations further include comparing the relevancy scores of the list of suggested tags to a threshold.
4. The system of claim 3, wherein the identifying the list of suggested tags includes selecting the list of suggested tags from a plurality of candidate tags based on at least the comparing the relevancy scores of the list of suggested tags to the threshold.
5. The system of claim 1, wherein the at least one of the suggested tags is indicative of at least one brand.
6. The system of claim 1, wherein the extracted features include at least one image-based feature extracted from an image portion of the media segment.
7. The system of claim 1, wherein the extracted features include at least one audio-based feature extracted from an audio portion of the media segment.
8. A method performed using at least one processor, the method comprising: extracting features from a media segment to generate a plurality of extracted features; determining weights for the plurality of extracted features, wherein each weight for each extracted feature is based on a type of automated feature extraction method used to generate the extracted feature; determining weighted features corresponding to the plurality of extracted features by weighing the extracted features using the weights determined based on the different types of automated feature extraction methods; searching a known tag database based on the weighted features, the known tag database including data indicative of extracted media features associated with one or more tags applied to respective ones of pre-tagged media segments; identifying, based on the searching the known tag database, a list of suggested tags corresponding to the media segment, each of the suggested tags in the list of suggested tags including a relevancy score; obtaining an indication of approval to associate at least one of the suggested tags with the media segment; and responsive to the obtaining the indication of approval, tagging the media segment with the at least one of the suggested tags by storing, in the known tag database, data indicative of the weighted features in association with the at least one of the suggested tags associated with the media segment.
9. The method of claim 8, wherein obtaining the indication of approval is performed by: presenting, via a user interface, a prompt requesting approval to associate the at least one of the suggested tags with the media segment; and receiving, via the user interface, the indication of approval.
10. The method of claim 8, further including comparing the relevancy scores of the list of suggested tags to a threshold.
11. The method of claim 10, wherein the identifying the list of suggested tags includes selecting the list of suggested tags from a plurality of candidate tags based on at least the comparing the relevancy scores of the list of suggested tags to the threshold.
12. The method of claim 8, wherein the at least one of the suggested tags is indicative of at least one brand.
13. The method of claim 8, wherein the extracted features include at least one image-based feature extracted from an image portion of the media segment.
14. The method of claim 8, wherein the extracted features include at least one audio-based feature extracted from an audio portion of the media segment.
15. A non-transitory computer readable storage medium having stored therein instructions that, upon execution by at least one processor, cause performance of operations comprising: extracting features from a media segment to generate a plurality of extracted features; determining weights for the plurality of extracted features, wherein each weight for each extracted feature is based on a type of automated feature extraction method used to generate the extracted feature; determining weighted features corresponding to the plurality of extracted features by weighing the extracted features using the weights determined based on the different types of automated feature extraction methods; searching a known tag database based on the weighted features, the known tag database including data indicative of extracted media features associated with one or more tags applied to respective ones of pre-tagged media segments; identifying, based on the searching the known tag database, a list of suggested tags corresponding to the media segment, each of the suggested tags in the list of suggested tags including a relevancy score; obtaining an indication of approval to associate at least one of the suggested tags with the media segment; and responsive to the obtaining the indication of approval, tagging the media segment with the at least one of the suggested tags by storing, in the known tag database, data indicative of the weighted features in association with the at least one of the suggested tags associated with the media segment.
16. The non-transitory computer readable storage medium of claim 15, wherein the obtaining the indication of approval is performed by: presenting, via a user interface, a prompt requesting approval to associate the at least one of the suggested tags with the media segment; and receiving, via the user interface, the indication of approval.
17. The non-transitory computer readable storage medium of claim 15, wherein the instructions further cause, upon execution by the at least one processor, performance of comparing the relevancy scores of the list of suggested tags to a threshold.
18. The non-transitory computer readable storage medium of claim 17, wherein the identifying the list of suggested tags includes selecting the list of suggested tags from a plurality of candidate tags based on at least the comparing the relevancy scores of the list of suggested tags to the threshold.
19. The non-transitory computer readable storage medium of claim 15, wherein the extracted features include at least one image-based feature extracted from an image portion of the media segment.
20. The non-transitory computer readable storage medium of claim 15, wherein the extracted features include at least one audio-based feature extracted from an audio portion of the media segment.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 31, 2023
April 15, 2025
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.